zhimingluo/nldf

Non-Local Deep Features for Salient Object Detection

This repository contains the code of the paper:

Luo Z, Mishra A, Achkar A, Eichel J, Li S-Z, Jodoin P-M, “Non-Local Deep Features for Salient Object Detection”, IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017)

The pre-train model and saliency map can be download at the project page.

https://sites.google.com/view/zhimingluo/nldf

The npy file the VGG-16 can be download at this link: https://github.com/machrisaa/tensorflow-vgg

nldf's Issues

loss变为NAN

您好！我将您代码中的网络结构简化为以下代码：
self.pool5_conv1 = self.Conv_2d(vgg.pool5, [3, 3, 512, 128], 0.01, padding='SAME', name='c1_')
self.contrast_1 = self.Contrast_Layer(self.pool5_conv1, 3)
self.pool5_conv2 = self.Conv_2d(tf.concat([self.pool5_conv1, self.contrast_1], axis=3), [3, 3, 256, 256], 0.01, padding='SAME', name='c2_')
self.pool5_conv3 = self.Conv_2d(self.pool5_conv2, [1, 1, 256, 2], 0.01, padding='SAME', name='c3_')
self.Score = tf.nn.conv2d_transpose(self.pool5_conv3, self.bilinear_upsample_weights(16, 2), output_shape=[1, 176, 176, 2], strides=[1, 16, 16, 1])
然后loss下降到0.32左右时，Loss就会变为NAN。（loss是边缘损失和交叉熵的和）
但是我运行你的网络结构时并不会出现NAN的问题，loss能降到很低。降低学习率我已经试了，然而并不行。
请问我应该如何解决这个问题呢？

AttributeError: 'Model' object has no attribute 'keep_prob'

I met the following error:
Traceback (most recent call last):
File "TestingModel.py", line 75, in
model.keep_prob: 1})
AttributeError: 'Model' object has no attribute 'keep_prob'
How can I fix it?

作者您好，能提供一下运行环境嘛？这边调试总出错，谢谢

请问PR曲线是用python 的代码运行的，能否提供下评测PR曲线的代码

请问PR曲线是用python 的代码运行的，能否提供下评测PR曲线的代码

loss函数实现是不是有问题？稍微复杂的图片loss就直接nan了

Crash while training

Hi,

I'm trying to train my own model according to your implementation.
Since I encounter some gradient error cause Nan or Inf error.

Below is the log when training crash

2018-10-31 02:12:13.561786: E tensorflow/core/kernels/check_numerics_op.cc:185] abnormal_detected_host @0x7fa89e206200 = {1, 0} Found Inf or NaN global norm.
Traceback (most recent call last):
  File "TrainingModel.py", line 112, in <module>
    model.label_holder: label_flip})
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 887, in run
    run_metadata_ptr)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1110, in _run
    feed_dict_tensor, options, run_metadata)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1286, in _do_run
    run_metadata)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/client/session.py", line 1308, in _do_call
    raise type(e)(node_def, op, message)
tensorflow.python.framework.errors_impl.InvalidArgumentError: Found Inf or NaN global norm. : Tensor had NaN values
     [[{{node VerifyFinite/CheckNumerics}} = CheckNumerics[T=DT_FLOAT, message="Found Inf or NaN global norm.", _device="/job:localhost/replica:0/task:0/device:GPU:0"](global_norm/global_norm)]]

Caused by op u'VerifyFinite/CheckNumerics', defined at:
  File "TrainingModel.py", line 42, in <module>
    grads, _ = tf.clip_by_global_norm(tf.gradients(model.Loss_Mean, tvars), max_grad_norm)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/clip_ops.py", line 259, in clip_by_global_norm
    "Found Inf or NaN global norm.")
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/numerics.py", line 45, in verify_tensor_all_finite
    verify_input = array_ops.check_numerics(t, message=msg)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/ops/gen_array_ops.py", line 817, in check_numerics
    "CheckNumerics", tensor=tensor, message=message, name=name)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/op_def_library.py", line 787, in _apply_op_helper
    op_def=op_def)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/util/deprecation.py", line 488, in new_func
    return func(*args, **kwargs)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 3272, in create_op
    op_def=op_def)
  File "/usr/local/lib/python2.7/dist-packages/tensorflow/python/framework/ops.py", line 1768, in __init__
    self._traceback = tf_stack.extract_stack()

InvalidArgumentError (see above for traceback): Found Inf or NaN global norm. : Tensor had NaN values
     [[{{node VerifyFinite/CheckNumerics}} = CheckNumerics[T=DT_FLOAT, message="Found Inf or NaN global norm.", _device="/job:localhost/replica:0/task:0/device:GPU:0"](global_norm/global_norm)]]

Could you help to comment about it.
I also wonder the tensorflow version or more detail for training environment of pre-build model.

Thanks.

TypeError: Value passed to parameter 'paddings' has DataType float32 not in list of allowed values: int32, int64

Hi, when I run the code in tf=1.3.0, I met the following error:
File "NLDF.py", line 126, in Contrast_Layer
return tf.subtract(input_, tf.nn.avg_pool(tf.pad(input_, [[0, 0], [h_s, h_s], [h_s, h_s], [0, 0]], 'SYMMETRIC'),
TypeError: Value passed to parameter 'paddings' has DataType float32 not in list of allowed values: int32, int64.
How can I fix it?